Use when searching code, logs, or repositories with tensor-grep; validating rg or AST parity; using tg MCP tools; checking GPU/search routing; or producing agent-friendly context, source, refs, or blast-radius output.
原文の言語: 英語
メニュー
SkillsMP は oimiragieo/tensor-grep から 40 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 40 件中 40 件を表示しています。
Use when searching code, logs, or repositories with tensor-grep; validating rg or AST parity; using tg MCP tools; checking GPU/search routing; or producing agent-friendly context, source, refs, or blast-radius output.
原文の言語: 英語
Use when writing or editing any tensor-grep doc of record (AGENTS.md, CLAUDE.md, root SKILL.md, docs/SESSION_HANDOFF.md, docs/CONTRACTS.md, docs/CONTINUATION_PLAN.md, docs/PAPER.md, README.md, docs/benchmarks.md, docs/gpu_crossover.md, mkdocs.yml, or any…
原文の言語: 英語
Use when deciding what counts as proof that a tensor-grep (tg) change works — before trusting a subagent's "tests pass", writing a new test, claiming a routing/docs/release fix is done, shipping a doc-drift/ranking/classification heuristic off green fixture…
原文の言語: 英語
Use when you need the domain theory behind tensor-grep's search/retrieval behavior, not just the command syntax — ripgrep exit codes (including the exit-2-but-kept partial-results contract)/PCRE2/binary-NUL-detection/-uuu/-- sentinels, ast-grep + tree-sitter…
原文の言語: 英語
Use when about to change, review, merge, or release ANY code in tensor-grep — adding a tg command or search flag, touching a backend/router/pipeline, editing CI/release/docs contracts, merging a PR, claiming a fix or speedup is done, or deciding whether a…
原文の言語: 英語
Use when adding, changing, or auditing a tg environment variable, CLI flag, or provider mode (native/lsp/hybrid); when a search flag silently leaks to ripgrep or a command misroutes; when deciding whether a config axis (GPU, LSP, classify, semantic) is…
原文の言語: 英語
Use when a tensor-grep (tg) run fails, hangs, returns wrong/empty/silently-degraded results, a CI check goes red, a release doesn't publish, a worktree agent's PR reports "No commits between main and <branch>" after a reported commit, or a…
原文の言語: 英語
Use when you need to MEASURE tensor-grep's health instead of eyeballing it -- interpreting a `tg doctor --json` field, reading a PASS/FAIL/SKIP from `tg dogfood` or `scripts/agent_readiness.py`, or explaining what a diagnostic field actually proves (and does…
原文の言語: 英語
Use when tg hangs, stalls, or runs for minutes on a large/unscoped repo; when `--deadline` "seems ignored" and a symbol query still overruns its budget; when working task #52 (CLOSED, end-to-end deadline ineffective on a ~1800-file TS repo) or #390 (CLOSED,…
原文の言語: 英語
Use when running the `tg` CLI day-to-day — exact syntax for orient, search --rank, defs/refs/callers/blast-radius, agent, docs-coverage, context, session open/refresh/serve/daemon, checkpoint, scan --ruleset, run, mcp, doctor, dogfood, upgrade; the…
原文の言語: 英語
Use when building, extending, or reviewing tensor-grep's APPROVED local hybrid semantic search — BM25 + CPU dense embeddings fused with Reciprocal Rank Fusion (RRF), no API key, no GPU (roadmap item #1). Load before adding a dense/embedding leg, RRF fusion, a…
原文の言語: 英語
Run a mechanical post-release governance sweep of the in-repo skills and docs after a release lands — version stamps that fall below the current tag, derived counts (language tier via _symbol_navigation_descriptor, skill count, tree-sitter package count) that…
原文の言語: 英語
Use when you need to run a CI lane locally that this repo's shared-box rules forbid (cargo test, tests/e2e/test_routing_parity.py, a full pytest matrix), when building or debugging scripts/ci-local/, when a local container run and the GitHub run disagree, or…
原文の言語: 英語
Use when about to claim, review, or dispute a speedup/regression in tensor-grep (tg vs rg, hot-cache, AST, agent-workflow, or GPU changes) — which benchmark script to run, how to read check_regression.py, the noise-floor/absolute-jitter rule for sub-10ms…
原文の言語: 英語
Use when vocabulary-mismatched queries need whole-repo hybrid search via tg find (BM25 + optional dense RRF, no regex pre-filter), or when verifying context-render vs edit-plan target agreement with tg route-test before trusting an edit plan. Distinct from tg…
原文の言語: 英語
Use when merging a release-bearing PR, writing a PR title for tensor-grep, diagnosing "why didn't my release publish" or "why hasn't npm/the docs site updated", running the post-publish dogfood, or making any external-facing speed/GPU/LSP/benchmark claim…
原文の言語: 英語
Use when writing a gated test that must pass identically on the dev desktop AND the CI pytest env (which lacks optional engines), constructing a HOSTILE fixture (permission denial, junction/symlink swap, network partition, disk-full, killed process, corrupted…
原文の言語: 英語
Use when asked to deep-dive, audit, fix, or drain the tensor-grep backlog, or to investigate and rank next work and produce SPEC/TDD plans without implementing. Triggers include "work the backlog", "what next", "investigate and plan", and backlog-completion…
原文の言語: 英語
Use when setting up the tensor-grep dev environment from a fresh clone, rebuilding the Rust/PyO3 extension or standalone `tg` binary after touching `rust_core/`, or debugging a build/toolchain problem — uv install, `maturin develop`, `cargo build`, the pinned…
原文の言語: 英語
Use when shipping an AUDIT-FIX PR for a verified H/M finding, running or resuming the codex-gated adversarial audit loop for a fix (behavioral RED -> minimal fix -> independent codex gate -> verify every finding with your OWN probes -> re-audit until SHIP),…
原文の言語: 英語
Use when a DEMAND_GATED board row must be measured before it may reopen: running a bounded, plan-frozen measurement that decides whether the row's reopen condition (its Trigger text, re-derived verbatim from origin/main) is satisfied. Covers frozen thresholds…
原文の言語: 英語
Use when demand is SATISFIED but product code is not yet authorized: writing or auditing docs/requirements+design+decisions packets, recording skip-Fable waivers, splitting PERF vs HONESTY sub-dispositions, or resisting "design on main = shipped" (A117/A122).…
原文の言語: 英語
Use when designing or evaluating tensor-grep as an enterprise agentic code-intelligence tool — tg prepare one-call edit readiness, PATH narrowing, agent --deadline, find/route-test/ledger, install-dense, EvidenceReceipts, review-bundle, GPU honesty,…
原文の言語: 英語
Use when about to "fix" or "optimize" something in tensor-grep that feels novel — before proposing PyO3/FFI for directory walking, re-enabling free-threading, adding a --json self-test, tightening a dependency upper-cap, blaming an IDF/ranking flip, trusting…
原文の言語: 英語
Use when you have a hunch, a candidate optimization, a novel technique, or an "I think X is faster/better/possible" idea for tensor-grep and must turn it into an ACCEPTED result or a DOCUMENTED RETIREMENT — the research discipline. Covers the evidence bar…
原文の言語: 英語
Use when you need the load-bearing design of tensor-grep and WHY it holds before touching cli/bootstrap.py, rust_core/src/main.rs, backends/, core/result.py, cli/main.py's native-delegation gate, routing, the agent capsule, or before reviewing/planning any…
原文の言語: 英語
Use when adding a new language to tensor-grep's tree-sitter symbol graph (defs/refs/callers/blast-radius, `tg source`, `tg imports`) — registering a `LanguageSpec` in `lang_registry.py`, writing a new `src/tensor_grep/cli/lang_<x>.py` extractor module,…
原文の言語: 英語
Use when writing or reviewing any code that confines filesystem access to a root (checkpoint snapshot/undo, LSP documentChanges, index reuse, install/upgrade, scan-writer paths) and must behave CORRECTLY on BOTH Windows and POSIX — especially junctions vs…
原文の言語: 英語
Use when working on index/reuse staleness detection — the Rust `.tg_index` reuse path, a cached parse/symbol/semantic index that is served on a LATER query, `staleness_reason` / `compute_tree_fingerprint` / mtime-size identity, or a "reused index must not…
原文の言語: 英語
Use tensor-grep for repository code search, symbol lookup, blast-radius analysis, and edit planning when solving codebase tasks or preparing patches.
原文の言語: 英語
Use when modifying, auditing, or testing an argv normalizer or a CLI front door that REWRITES one invocation shape into another (bootstrap `_normalize_search_invocation` / `main_entry`, `SEARCH_OPTION_FIRST_FLAGS`→`tg search ...` in rust_core), adding or…
原文の言語: 英語
Use when coordinating multiple agents on the same repo with tg ledger — advisory claim/release/list (Slice 1) and content-addressed finding record/find reuse (Slice 2). Never blocks edits; overlaps are informational. Distinct from tg evidence emit (produces…
原文の言語: 英語
Use when an agent needs one-call edit readiness before changing code — tg prepare returns primary target, confidence, callers/blast-radius floor, validation commands, and claim/evidence coordination hooks. Prefer over the multi-step…
原文の言語: 英語
Use when stress-testing tensor-grep against a multi-project workspace — orientation, scoped search, tg find, prepare, route-test, ledger, install-dense, symbol graphs, GPU, evidence, sessions, readiness gates. Not the PyPI release dogfood harness.
原文の言語: 英語
Use when planning, building, reviewing, or prioritizing any slice of the world-class roadmap — the agentic EDIT-CONTROL PLANE thesis (not faster grep); the S1 fail-closed edit tickets + verify-edit with ESCROWED CI-held-key evidence; S2 registration-aware…
原文の言語: 英語
Use when packaging tensor-grep outputs for enterprise change review — review-bundle create/verify requires a rewrite audit --manifest (not a capsule); optionally attach scan JSON and checkpoint IDs; pair with evidence emit and audit-history.
原文の言語: 英語
Use when exercising tensor-grep experimental GPU paths — devices/doctor probes, --gpu-device-ids search, agent GPU evidence, calibrate crossover. Distinguishes inventory detection from actual NativeGpuBackend promotion proof; CPU auto-fallback is not a GPU…
原文の言語: 英語
Use when searching across a multi-project workspace root (many sibling repos) with tensor-grep — bare unscoped search is refused; scope with --glob/--type/--max-depth or opt in with --allow-broad-generated-scan; prefer per-repo paths for agent/symbol/find…
原文の言語: 英語
Use when scoping, pitching, planning, or judging a SOTA-advancing bet in tensor-grep (tg) — the OPEN research problems, not a bug fix or a shipped feature. Load when asked "where can tg beat the state of the art / what's the moat / is this worth building", or…
原文の言語: 英語
Use tensor-grep for repository code search, symbol lookup, blast-radius analysis, and edit planning when solving codebase tasks or preparing patches.
原文の言語: 英語